Saved in:
Bibliographic Details
Main Authors: Patel, Dhruvesh, Maram, Durga Prasad, Chintha, Sai Sreenivas, Rozonoyer, Benjamin, McCallum, Andrew
Format: Preprint
Published: 2025
Subjects:
Online Access:https://arxiv.org/abs/2512.17065
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866918256103653376
author Patel, Dhruvesh
Maram, Durga Prasad
Chintha, Sai Sreenivas
Rozonoyer, Benjamin
McCallum, Andrew
author_facet Patel, Dhruvesh
Maram, Durga Prasad
Chintha, Sai Sreenivas
Rozonoyer, Benjamin
McCallum, Andrew
contents In recent years, there has been a resurgence of interest in non-autoregressive text generation in the context of general language modeling. Unlike the well-established autoregressive language modeling paradigm, which has a plethora of standard training and inference libraries, implementations of non-autoregressive language modeling have largely been bespoke making it difficult to perform systematic comparisons of different methods. Moreover, each non-autoregressive language model typically requires it own data collation, loss, and prediction logic, making it challenging to reuse common components. In this work, we present the XLM python package, which is designed to make implementing small non-autoregressive language models faster with a secondary goal of providing a suite of small pre-trained models (through a companion xlm-models package) that can be used by the research community. The code is available at https://github.com/dhruvdcoder/xlm-core.
format Preprint
id arxiv_https___arxiv_org_abs_2512_17065
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle XLM: A Python package for non-autoregressive language models
Patel, Dhruvesh
Maram, Durga Prasad
Chintha, Sai Sreenivas
Rozonoyer, Benjamin
McCallum, Andrew
Computation and Language
In recent years, there has been a resurgence of interest in non-autoregressive text generation in the context of general language modeling. Unlike the well-established autoregressive language modeling paradigm, which has a plethora of standard training and inference libraries, implementations of non-autoregressive language modeling have largely been bespoke making it difficult to perform systematic comparisons of different methods. Moreover, each non-autoregressive language model typically requires it own data collation, loss, and prediction logic, making it challenging to reuse common components. In this work, we present the XLM python package, which is designed to make implementing small non-autoregressive language models faster with a secondary goal of providing a suite of small pre-trained models (through a companion xlm-models package) that can be used by the research community. The code is available at https://github.com/dhruvdcoder/xlm-core.
title XLM: A Python package for non-autoregressive language models
topic Computation and Language
url https://arxiv.org/abs/2512.17065